Upload app.py

app.py

@@ -6,11 +6,22 @@ import os
 import uuid
 import requests
 import logging
-from llama_cpp import Llama
+import subprocess
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
+# Function to install requirements
+def install_requirements():
+    try:
+        subprocess.check_call([os.sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
+        logging.info("Requirements installed successfully.")
+    except subprocess.CalledProcessError as e:
+        logging.error(f"Failed to install requirements: {e}")
+
+# Install requirements
+install_requirements()
+
 # Create the directory if it doesn't exist
 local_dir = "models"
 os.makedirs(local_dir, exist_ok=True)
@@ -35,7 +46,7 @@ def download_model(repo_id, filename, save_path):
 
 # Download the model if it doesn't exist
 if not os.path.exists(model_path):
-    download_model("PurpleAILAB/Llama3.2-3B-uncensored-SQLi-Q4_K_M-GGUF", filename, model_path)
+    download_model("PurpleAILAB/Llama3.2-3B-uncensored-SQLi-Q4_K_M-GGUF", filename)
 
 def respond(
     message,
@@ -55,7 +66,7 @@ def respond(
     # Load the model with the maximum context length and control the maximum tokens in the response
     llm = Llama(
         model_path=model_path,
-        n_ctx=5072,  # Set the maximum context length
+        n_ctx=5000,  # Set the maximum context length
         max_tokens=512  # Control the maximum number of tokens generated in the response
     )